Picture for Yanyun Qu

Yanyun Qu

Gradient Projection For Parameter-Efficient Continual Learning

Add code
May 22, 2024
Viaarxiv icon

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception

Add code
May 12, 2024
Viaarxiv icon

Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification

May 09, 2024
Viaarxiv icon

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

Add code
Apr 08, 2024
Viaarxiv icon

Progressive Contrastive Learning with Multi-Prototype for Unsupervised Visible-Infrared Person Re-identification

Feb 29, 2024
Viaarxiv icon

Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification

Jan 12, 2024
Viaarxiv icon

CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data

Add code
Dec 14, 2023
Viaarxiv icon

Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation

Dec 13, 2023
Figure 1 for Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Figure 2 for Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Figure 3 for Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Figure 4 for Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Viaarxiv icon

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

Add code
Dec 04, 2023
Figure 1 for COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Figure 2 for COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Figure 3 for COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Figure 4 for COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Viaarxiv icon

BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation

Aug 12, 2023
Figure 1 for BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Figure 2 for BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Figure 3 for BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Figure 4 for BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Viaarxiv icon